A Deep Boltzmann Machine-Based Approach for Robust Image Denoising

A Deep Boltzmann Machine (DBM) is composed of a stack of learners called Restricted Boltzmann Machines (RBMs), which correspond to a specific kind of stochastic energy-based networks. In this work, a DBM is applied to a robust image denoising by minimizing the contribution of some of its top nodes, called “noise nodes”, which often get excited when noise pixels are present in the given images. After training the DBM with noise and clean images, the detection and deactivation of the noise nodes allow reconstructing images with great quality, eliminating most of their noise. The results obtained from important public image datasets showed the validity of the proposed approach.

[1]  Aggelos K. Katsaggelos,et al.  Digital image restoration , 2012, IEEE Signal Process. Mag..

[2]  Geoffrey E. Hinton,et al.  Robust Boltzmann Machines for recognition and denoising , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Mohammad Pezeshki,et al.  Deep Belief Networks for Image Denoising , 2014, ICLR.

[4]  João Paulo Papa,et al.  Projections Onto Convex Sets through Particle Swarm Optimization and its application for remote sensing image restoration , 2010, Pattern Recognit. Lett..

[5]  João Paulo Papa,et al.  Projections onto convex sets parameter estimation through harmony search and its application for image restoration , 2015, Natural Computing.

[6]  Aggelos K. Katsaggelos,et al.  Image restoration using a modified Hopfield network , 1992, IEEE Trans. Image Process..

[7]  Emile H. L. Aarts,et al.  Boltzmann machines , 1998 .

[8]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[9]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[10]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[11]  Yi Sun,et al.  A modified Hopfield neural network used in bilevel image restoration and reconstruction , 1992, [Proceedings] Singapore ICCS/ISITA `92.

[12]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[13]  Ling Shao,et al.  Image Blur Classification and Parameter Identification Using Two-stage Deep Belief Networks , 2013, BMVC.

[14]  Geoffrey E. Hinton,et al.  An Efficient Learning Procedure for Deep Boltzmann Machines , 2012, Neural Computation.